mm/gup: migrate pinned pages out of movable zone

We should not pin pages in ZONE_MOVABLE.  Currently, we do not pin only
movable CMA pages.  Generalize the function that migrates CMA pages to
migrate all movable pages.  Use is_pinnable_page() to check which pages
need to be migrated

Link: https://lkml.kernel.org/r/20210215161349.246722-10-pasha.tatashin@soleen.comSigned-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sasha Levin <sashal@kernel.org>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Tyler Hicks <tyhicks@linux.microsoft.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/migrate.h

@@ -27,6 +27,7 @@ enum migrate_reason {
 	MR_MEMPOLICY_MBIND,
 	MR_NUMA_MISPLACED,
 	MR_CONTIG_RANGE,
+	MR_LONGTERM_PIN,
 	MR_TYPES
 };
 

include/linux/mmzone.h

@@ -407,8 +407,13 @@ enum zone_type {
 	 * to increase the number of THP/huge pages. Notable special cases are:
 	 *
 	 * 1. Pinned pages: (long-term) pinning of movable pages might
-	 *    essentially turn such pages unmovable. Memory offlining might
-	 *    retry a long time.
+	 *    essentially turn such pages unmovable. Therefore, we do not allow
+	 *    pinning long-term pages in ZONE_MOVABLE. When pages are pinned and
+	 *    faulted, they come from the right zone right away. However, it is
+	 *    still possible that address space already has pages in
+	 *    ZONE_MOVABLE at the time when pages are pinned (i.e. user has
+	 *    touches that memory before pinning). In such case we migrate them
+	 *    to a different zone. When migration fails - pinning fails.
 	 * 2. memblock allocations: kernelcore/movablecore setups might create
 	 *    situations where ZONE_MOVABLE contains unmovable allocations
 	 *    after boot. Memory offlining and allocations fail early.

include/trace/events/migrate.h

@@ -20,7 +20,8 @@
 	EM( MR_SYSCALL,		"syscall_or_cpuset")		\
 	EM( MR_MEMPOLICY_MBIND,	"mempolicy_mbind")		\
 	EM( MR_NUMA_MISPLACED,	"numa_misplaced")		\
-	EMe(MR_CONTIG_RANGE,	"contig_range")
+	EM( MR_CONTIG_RANGE,	"contig_range")			\
+	EMe(MR_LONGTERM_PIN,	"longterm_pin")
 
 /*
  * First define the enums in the above macros to be exported to userspace

mm/gup.c

@@ -87,11 +87,12 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page,
 		int orig_refs = refs;
 
 		/*
-		 * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast
-		 * path, so fail and let the caller fall back to the slow path.
+		 * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a
+		 * right zone, so fail and let the caller fall back to the slow
+		 * path.
 		 */
-		if (unlikely(flags & FOLL_LONGTERM) &&
-				is_migrate_cma_page(page))
+		if (unlikely((flags & FOLL_LONGTERM) &&
+			     !is_pinnable_page(page)))
 			return NULL;
 
 		/*
@@ -1600,17 +1601,17 @@ struct page *get_dump_page(unsigned long addr)
 }
 #endif /* CONFIG_ELF_CORE */
 
-#ifdef CONFIG_CMA
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
-					unsigned long start,
-					unsigned long nr_pages,
-					struct page **pages,
-					struct vm_area_struct **vmas,
-					unsigned int gup_flags)
+#ifdef CONFIG_MIGRATION
+static long check_and_migrate_movable_pages(struct mm_struct *mm,
+					    unsigned long start,
+					    unsigned long nr_pages,
+					    struct page **pages,
+					    struct vm_area_struct **vmas,
+					    unsigned int gup_flags)
 {
 	unsigned long i, isolation_error_count;
 	bool drain_allow;
-	LIST_HEAD(cma_page_list);
+	LIST_HEAD(movable_page_list);
 	long ret = nr_pages;
 	struct page *prev_head, *head;
 	struct migration_target_control mtc = {
@@ -1628,13 +1629,12 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 			continue;
 		prev_head = head;
 		/*
-		 * If we get a page from the CMA zone, since we are going to
-		 * be pinning these entries, we might as well move them out
-		 * of the CMA zone if possible.
+		 * If we get a movable page, since we are going to be pinning
+		 * these entries, try to move them out if possible.
 		 */
-		if (is_migrate_cma_page(head)) {
+		if (!is_pinnable_page(head)) {
 			if (PageHuge(head)) {
-				if (!isolate_huge_page(head, &cma_page_list))
+				if (!isolate_huge_page(head, &movable_page_list))
 					isolation_error_count++;
 			} else {
 				if (!PageLRU(head) && drain_allow) {
@@ -1646,7 +1646,7 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 					isolation_error_count++;
 					continue;
 				}
-				list_add_tail(&head->lru, &cma_page_list);
+				list_add_tail(&head->lru, &movable_page_list);
 				mod_node_page_state(page_pgdat(head),
 						    NR_ISOLATED_ANON +
 						    page_is_file_lru(head),
@@ -1659,10 +1659,10 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 	 * If list is empty, and no isolation errors, means that all pages are
 	 * in the correct zone.
 	 */
-	if (list_empty(&cma_page_list) && !isolation_error_count)
+	if (list_empty(&movable_page_list) && !isolation_error_count)
 		return ret;
 
-	if (!list_empty(&cma_page_list)) {
+	if (!list_empty(&movable_page_list)) {
 		/*
 		 * drop the above get_user_pages reference.
 		 */
@@ -1672,12 +1672,12 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 			for (i = 0; i < nr_pages; i++)
 				put_page(pages[i]);
 
-		ret = migrate_pages(&cma_page_list, alloc_migration_target,
+		ret = migrate_pages(&movable_page_list, alloc_migration_target,
 				    NULL, (unsigned long)&mtc, MIGRATE_SYNC,
-				    MR_CONTIG_RANGE);
+				    MR_LONGTERM_PIN);
 		if (ret) {
-			if (!list_empty(&cma_page_list))
-				putback_movable_pages(&cma_page_list);
+			if (!list_empty(&movable_page_list))
+				putback_movable_pages(&movable_page_list);
 			return ret > 0 ? -ENOMEM : ret;
 		}
 
@@ -1696,16 +1696,16 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm,
 	goto check_again;
 }
 #else
-static long check_and_migrate_cma_pages(struct mm_struct *mm,
-					unsigned long start,
-					unsigned long nr_pages,
-					struct page **pages,
-					struct vm_area_struct **vmas,
-					unsigned int gup_flags)
+static long check_and_migrate_movable_pages(struct mm_struct *mm,
+					    unsigned long start,
+					    unsigned long nr_pages,
+					    struct page **pages,
+					    struct vm_area_struct **vmas,
+					    unsigned int gup_flags)
 {
 	return nr_pages;
 }
-#endif /* CONFIG_CMA */
+#endif /* CONFIG_MIGRATION */
 
 /*
  * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
@@ -1729,8 +1729,9 @@ static long __gup_longterm_locked(struct mm_struct *mm,
 
 	if (gup_flags & FOLL_LONGTERM) {
 		if (rc > 0)
-			rc = check_and_migrate_cma_pages(mm, start, rc, pages,
-							 vmas, gup_flags);
+			rc = check_and_migrate_movable_pages(mm, start, rc,
+							     pages, vmas,
+							     gup_flags);
 		memalloc_pin_restore(flags);
 	}
 	return rc;